© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 73950
    Prev
    Next
    INDEX
    Explanations

    ing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -compose
    -0.06
    registr
    -0.06
    -orange
    -0.06
    vp
    -0.06
     ауд
    -0.06
     bottoms
    -0.06
    El
    -0.06
     UnityEngine
    -0.06
    žila
    -0.06
     과정
    -0.06
    POSITIVE LOGITS
     excav
    0.07
    UCKET
    0.07
     extracting
    0.07
     antique
    0.06
    чя
    0.06
    ��
    0.06
    _filter
    0.06
     aire
    0.06
    roc
    0.06
     моря
    0.06
    Activations Density 0.013%

    No Known Activations